Multimodal survival prediction in advanced pancreatic cancer using machine learning

Background: Existing risk scores appear insufficient to assess the individual survival risk of patients with advanced pancreatic ductal adenocarcinoma (PDAC) and do not take advantage of the variety of parameters that are collected during clinical care. Methods: In this retrospective study, we built a random survival forest model from clinical data of 203 patients with advanced PDAC. The parameters were assessed before initiation of systemic treatment and included age, CA19-9, Creactive protein, metastatic status, neutrophil-to-lymphocyte ratio and total serum protein level. Separate models including imaging and molecular parameters were built for subgroups. Results: Over the entire cohort, a model based on clinical parameters achieved a c-index of 0.71. Our approach outperformed the American Joint Committee on Cancer (AJCC) staging system and the modified Glasgow Prognostic Score (mGPS) in the identification of high- and low-risk subgroups. Inclusion of the KRAS p.G12D mutational status could further improve the prediction, whereas radiomics data of the primary tumor only showed little benefit. In an external validation cohort of PDAC patients with liver metastases, our model achieved a c-index of 0.67 (mGPS: 0.59). Conclusions: The combination of multimodal data and machine-learning algorithms holds potential for personalized prognostication in advanced PDAC already at diagnosis.

Automated summary

In this study, a random survival forest model was built using clinical data of patients with advanced PDAC to predict prognosis. The results showed that this approach outperformed existing scoring systems in identifying high- and low-risk subgroups. The inclusion of KRAS p.G12D mutation status further improved the prediction, while radiomics data of the primary tumor had little impact on the results.